Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2535 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0602. Min Act: -0.0002

Data Index: 624335 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0579. Min Act: -0.0003

Data Index: 832411 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0557. Min Act: -0.0003

Data Index: 469998 (C4 (Web Text))

Max Activating Token Index: 59

Text #3

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0504. Min Act: -0.0003

Data Index: 380017 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0528. Min Act: -0.0002

Data Index: 507166 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0527. Min Act: -0.0002

Data Index: 74883 (C4 (Web Text))

Max Activating Token Index: 362

Text #6

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0505. Min Act: -0.0002

Data Index: 989330 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0490. Min Act: -0.0003

Data Index: 705389 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0507. Min Act: -0.0003

Data Index: 855738 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0469. Min Act: -0.0003

Data Index: 196763 (C4 (Web Text))

Max Activating Token Index: 18

Text #10

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0485. Min Act: -0.0003

Data Index: 89491 (C4 (Web Text))

Max Activating Token Index: 922

Text #11

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0474. Min Act: -0.0002

Data Index: 1127015 (C4 (Web Text))

Max Activating Token Index: 127

Text #12

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0448. Min Act: -0.0003

Data Index: 832763 (C4 (Web Text))

Max Activating Token Index: 69

Text #13

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0418. Min Act: -0.0002

Data Index: 1343088 (C4 (Web Text))

Max Activating Token Index: 6

Text #14

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0420. Min Act: -0.0003

Data Index: 1198983 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0429. Min Act: -0.0002

Data Index: 350604 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0418. Min Act: -0.0002

Data Index: 1280661 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0411. Min Act: -0.0002

Data Index: 845740 (C4 (Web Text))

Max Activating Token Index: 5

Text #18

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0410. Min Act: -0.0002

Data Index: 1087775 (C4 (Web Text))

Max Activating Token Index: 822

Text #19

Max Range: 0.0602. Min Range: -0.0602

Max Act: 0.0395. Min Act: -0.0003

Data Index: 303290 (C4 (Web Text))

Max Activating Token Index: 592